How beejayc/dt_lennyrag_rebuild works
LennyHub is a transcript-search product: transcripts are indexed into vector and knowledge-graph representations, then users query them through a web UI or CLI and receive synthesized answers. The graph distinguishes the documented ingestion, retrieval, synthesis, and graph-exploration capabilities. Some retrieval and persistence internals are provided by RAG-Anything/LightRAG and are not shown in the excerpts, so their internal calls are not expanded.
Main entry points: query_worker.py Query worker · setup_rag.py Index orchestrator · streamlit_app.py Web application · query_rag.py Query CLI
Components 16
Transcript ingestion
- Index orchestrator
setup_rag.py - RAG framework
Question answering
- Query worker
query_worker.py
Index and storage
- Qdrant configuration
qdrant_config.py - Vector database
- Knowledge graph
User interfaces
- Web application
streamlit_app.py - Query CLI
query_rag.py - Source-attribution CLI
query_with_sources.py - Chunk-debug CLI
query_rag_with_chunks.py
Graph exploration
- Graph exporter
export_graph.py - Graph explorer service
serve_graph.py
Other components
- Questioner
- Podcast transcripts
- Azure OpenAI
- Answer and citations
Connections 28
- Index orchestrator → Podcast transcripts: reads files
setup_rag.py - Index orchestrator → RAG framework: indexes transcripts
setup_rag.py - Index orchestrator → Qdrant configuration: checks and prepares
setup_rag.py - RAG framework → Vector database: stores vectors
README.md - RAG framework → Knowledge graph: stores relationships
README.md - Index orchestrator → Azure OpenAI: uses embeddings and model
setup_rag.py - Questioner → Web application: asks question
README.md - Web application → Query worker: launches subprocess
streamlit_app.py - Query worker → RAG framework: runs query
query_worker.py - Query worker → Qdrant configuration: loads working directory
query_worker.py - Query worker → Azure OpenAI: uses embeddings and model
query_worker.py - RAG framework → Vector database: retrieves relevant chunks
README.md - RAG framework → Knowledge graph: retrieves graph context
README.md - RAG framework → Azure OpenAI: synthesizes answer
README.md - Web application → Qdrant configuration: checks health and stats
streamlit_app.py - Query worker → Answer and citations: returns result
query_worker.py - Questioner → Query CLI: submits query
query_rag.py - Query CLI → RAG framework: runs query
query_rag.py - Query CLI → Azure OpenAI: configures model and embeddings
query_rag.py - Questioner → Source-attribution CLI: submits query
query_with_sources.py - Source-attribution CLI → RAG framework: runs query
query_with_sources.py - Source-attribution CLI → Azure OpenAI: configures model and embeddings
query_with_sources.py - Questioner → Chunk-debug CLI: submits query
query_rag_with_chunks.py - Chunk-debug CLI → RAG framework: runs query
query_rag_with_chunks.py - Chunk-debug CLI → Azure OpenAI: configures model and embeddings
query_rag_with_chunks.py - Knowledge graph → Graph exporter: provides GraphML
export_graph.py - Graph explorer service → Graph exporter: uses exporter
serve_graph.py - Graph explorer service → Questioner: presents graph
README.md